© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110333
    Prev
    Next
    INDEX
    Explanations

    actions followed by grammatical connectors

    np_acts-logits-general · gemini-2.5-flash-lite

    lack or absence of something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    毁
    0.51
    adaş
    0.47
    嬿
    0.45
    UpdateTime
    0.43
    ança
    0.42
    mış
    0.41
    不过
    0.41
    -${
    0.41
    :${
    0.41
     помнить
    0.41
    POSITIVE LOGITS
    the
    0.53
     समूहों
    0.52
    thebetter
    0.46
    tracks
    0.44
    tiered
    0.44
     ایسے
    0.43
     populist
    0.43
    RENCH
    0.43
    training
    0.42
    ILS
    0.42
    Activations Density 0.001%

    No Known Activations